SlideShare a Scribd company logo
A Framework for Understanding
Unintended consequences of
Machine Learning
Author: Harini Suresh (MIT), John V. Guttag(MIT)
Presented: Chenguang Xu “Shine”
The Problem with Biased data
• Various unwanted consequences of ML algorithm arise in
some way from biased data.
• Bias refers to an unintended or potentially harmful
property of the data.

• Data is a product of many factors, and is the product of a
process
An illustrative Scenario
Lack of data on women, introducing
more data solved the issue.
The use of a proxy label (human assessment of
quality) versus the true label (actual qualification)
allowed the model to discriminate by gender.
Five Sources of Bias in ML
Historical Bias
It is a fundamental, structural issue with the
very first step of the data generation process.
Representation Bias
• It arises when defining and sampling from a population. 

• It can arise for several reasons:
• The sampling methods only reach a portion of the
population.

• The population of interest has changed or is distinct
from the population used during model training.
Representation Bias (cont.)
Shankar, Shreya, et al. "No classification without representation: Assessing geodiversity issues in open
data sets for the developing world." arXiv preprint arXiv:1711.08536 (2017).
Representation Bias (cont.)
Photos of bridegrooms from
different countries aligned by the
log-likelihood that the classifier
trained on Open Images assigns to
the bridegroom class. 

Shankar, Shreya, et al. "No classification without representation: Assessing geodiversity issues in open
data sets for the developing world." arXiv preprint arXiv:1711.08536 (2017).
Measurement Bias
• It arises when subsequently choosing and measuring the
particular features of interest.

• It can arise in several ways:
• The granularity of data varies across groups.

• The quality of data varies across groups.

• The defined classification task is an oversimplification.
• It arises when a one-size-fit-all model is used for groups
with different conditional distributions. 

Aggregation Bias
Evaluation Bias
• It occurs when the evaluation and/or benchmark data for
an algorithm doesn’t represent the target population.
Buolamwini, Joy, and Timnit Gebru. "Gender shades: Intersectional accuracy disparities in
commercial gender classification." Conference on Fairness, Accountability and Transparency.
2018.
Formalizations and Mitigations
• A data generation and ML pipeline viewed as a series of
mapping functions.
Mitigating Aggregation Bias:
• adjusting g

• change r or t for transforming
the data
Mitigating Evaluation Bias:
• redefine k

• adjusting X, Y
^ ^
Mitigating Representation Bias:
• improve s
Measurement and historical Bias:
• adjust s will likely be ineffective
?

More Related Content

Similar to Lab presentation (a framework for understanding unintended consequences of machine learning)

AI ETHICS.pptx
AI ETHICS.pptxAI ETHICS.pptx
AI ETHICS.pptx
AthenaJoseph2
 
AI Bias Oxford 2017
AI Bias Oxford 2017AI Bias Oxford 2017
AI Bias Oxford 2017
Dr Janet Bastiman
 
Fair AI
Fair AIFair AI
Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...
Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...
Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...
Mary Loftus
 
GeneralizibilityFairness - DEFirst Reading Group
GeneralizibilityFairness - DEFirst Reading GroupGeneralizibilityFairness - DEFirst Reading Group
GeneralizibilityFairness - DEFirst Reading Group
Hossein A. (Saeed) Rahmani
 
Fairness in Machine Learning
Fairness in Machine LearningFairness in Machine Learning
Fairness in Machine Learning
Delip Rao
 
Fairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML SystemsFairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML Systems
Krishnaram Kenthapadi
 
GA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATION
GA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATIONGA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATION
GA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATION
ijfcstjournal
 
Methods of sample selection
Methods of sample selectionMethods of sample selection
Methods of sample selection
Jeferson L. Feuser
 
Scientific Method to Hire Great Scrum Masters
Scientific Method to Hire Great Scrum MastersScientific Method to Hire Great Scrum Masters
Scientific Method to Hire Great Scrum Masters
Pavel Dabrytski
 
KnowMe and ShareMe: understanding automatically discovered personality traits...
KnowMe and ShareMe: understanding automatically discovered personality traits...KnowMe and ShareMe: understanding automatically discovered personality traits...
KnowMe and ShareMe: understanding automatically discovered personality traits...
Leon Gou
 
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Krishnaram Kenthapadi
 
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Krishnaram Kenthapadi
 
Measures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairnessMeasures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairness
Manojit Nandi
 
Fairness in Search & RecSys 네이버 검색 콜로키움 김진영
Fairness in Search & RecSys 네이버 검색 콜로키움 김진영Fairness in Search & RecSys 네이버 검색 콜로키움 김진영
Fairness in Search & RecSys 네이버 검색 콜로키움 김진영
Jin Young Kim
 
Fairness in Machine Learning @Codemotion
Fairness in Machine Learning @CodemotionFairness in Machine Learning @Codemotion
Fairness in Machine Learning @Codemotion
Azzurra Ragone
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)
Krishnaram Kenthapadi
 
Reproducibility from an infomatics perspective
Reproducibility from an infomatics perspectiveReproducibility from an infomatics perspective
Reproducibility from an infomatics perspective
Micah Altman
 
Scientific Reproducibility from an Informatics Perspective
Scientific Reproducibility from an Informatics PerspectiveScientific Reproducibility from an Informatics Perspective
Scientific Reproducibility from an Informatics Perspective
Micah Altman
 
Doing Grounded Thoery
Doing Grounded ThoeryDoing Grounded Thoery
Doing Grounded Thoery
Leo Casey
 

Similar to Lab presentation (a framework for understanding unintended consequences of machine learning) (20)

AI ETHICS.pptx
AI ETHICS.pptxAI ETHICS.pptx
AI ETHICS.pptx
 
AI Bias Oxford 2017
AI Bias Oxford 2017AI Bias Oxford 2017
AI Bias Oxford 2017
 
Fair AI
Fair AIFair AI
Fair AI
 
Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...
Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...
Ways of seeing learning - 2017v1.0 - NUI Galway University of Limerick postgr...
 
GeneralizibilityFairness - DEFirst Reading Group
GeneralizibilityFairness - DEFirst Reading GroupGeneralizibilityFairness - DEFirst Reading Group
GeneralizibilityFairness - DEFirst Reading Group
 
Fairness in Machine Learning
Fairness in Machine LearningFairness in Machine Learning
Fairness in Machine Learning
 
Fairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML SystemsFairness and Privacy in AI/ML Systems
Fairness and Privacy in AI/ML Systems
 
GA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATION
GA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATIONGA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATION
GA-CFS APPROACH TO INCREASE THE ACCURACY OF ESTIMATES IN ELECTIONS PARTICIPATION
 
Methods of sample selection
Methods of sample selectionMethods of sample selection
Methods of sample selection
 
Scientific Method to Hire Great Scrum Masters
Scientific Method to Hire Great Scrum MastersScientific Method to Hire Great Scrum Masters
Scientific Method to Hire Great Scrum Masters
 
KnowMe and ShareMe: understanding automatically discovered personality traits...
KnowMe and ShareMe: understanding automatically discovered personality traits...KnowMe and ShareMe: understanding automatically discovered personality traits...
KnowMe and ShareMe: understanding automatically discovered personality traits...
 
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
 
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
 
Measures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairnessMeasures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairness
 
Fairness in Search & RecSys 네이버 검색 콜로키움 김진영
Fairness in Search & RecSys 네이버 검색 콜로키움 김진영Fairness in Search & RecSys 네이버 검색 콜로키움 김진영
Fairness in Search & RecSys 네이버 검색 콜로키움 김진영
 
Fairness in Machine Learning @Codemotion
Fairness in Machine Learning @CodemotionFairness in Machine Learning @Codemotion
Fairness in Machine Learning @Codemotion
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)
 
Reproducibility from an infomatics perspective
Reproducibility from an infomatics perspectiveReproducibility from an infomatics perspective
Reproducibility from an infomatics perspective
 
Scientific Reproducibility from an Informatics Perspective
Scientific Reproducibility from an Informatics PerspectiveScientific Reproducibility from an Informatics Perspective
Scientific Reproducibility from an Informatics Perspective
 
Doing Grounded Thoery
Doing Grounded ThoeryDoing Grounded Thoery
Doing Grounded Thoery
 

Recently uploaded

Histology of Muscle types histology o.ppt
Histology of Muscle types histology o.pptHistology of Muscle types histology o.ppt
Histology of Muscle types histology o.ppt
SamanArshad11
 
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
ginni singh$A17
 
Towards an Analysis-Ready, Cloud-Optimised service for FAIR fusion data
Towards an Analysis-Ready, Cloud-Optimised service for FAIR fusion dataTowards an Analysis-Ready, Cloud-Optimised service for FAIR fusion data
Towards an Analysis-Ready, Cloud-Optimised service for FAIR fusion data
Samuel Jackson
 
VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...
satpalsheravatmumbai
 
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
NABLAS株式会社
 
the potential of the development of the Ford–Fulkerson algorithm to solve the...
the potential of the development of the Ford–Fulkerson algorithm to solve the...the potential of the development of the Ford–Fulkerson algorithm to solve the...
the potential of the development of the Ford–Fulkerson algorithm to solve the...
huseindihon
 
Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...
Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...
Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...
weiwchu
 
DU degree offer diploma Transcript
DU degree offer diploma TranscriptDU degree offer diploma Transcript
DU degree offer diploma Transcript
uapta
 
🚂🚘 Premium Girls Call Guwahati 🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...
🚂🚘 Premium Girls Call Guwahati  🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...🚂🚘 Premium Girls Call Guwahati  🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...
🚂🚘 Premium Girls Call Guwahati 🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...
kuldeepsharmaks8120
 
Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...
Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...
Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...
revolutionary575
 
🚂🚘 Premium Girls Call Bangalore 🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...
🚂🚘 Premium Girls Call Bangalore  🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...🚂🚘 Premium Girls Call Bangalore  🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...
🚂🚘 Premium Girls Call Bangalore 🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...
bhupeshkumar0889
 
Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...
Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...
Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...
sheetal singh$A17
 
DataScienceConcept_Kanchana_Weerasinghe.pptx
DataScienceConcept_Kanchana_Weerasinghe.pptxDataScienceConcept_Kanchana_Weerasinghe.pptx
DataScienceConcept_Kanchana_Weerasinghe.pptx
Kanchana Weerasinghe
 
History and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big DataHistory and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big Data
Jongwook Woo
 
Why_are_we_hypnotizing_ourselves-_ATeggin-1.pdf
Why_are_we_hypnotizing_ourselves-_ATeggin-1.pdfWhy_are_we_hypnotizing_ourselves-_ATeggin-1.pdf
Why_are_we_hypnotizing_ourselves-_ATeggin-1.pdf
Alexander Teggin
 
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
tanupasswan6
 
VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...
VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...
VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...
sukaniyasunnu
 
Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...
Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...
Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...
sheetal singh$A17
 
Cyber Insurance Mathematical Model & Pricing
Cyber Insurance Mathematical Model & PricingCyber Insurance Mathematical Model & Pricing
Cyber Insurance Mathematical Model & Pricing
BaraDaniel1
 
Potential Uses of the Floyd-Warshall Algorithm as appropriate
Potential Uses of the Floyd-Warshall Algorithm as appropriatePotential Uses of the Floyd-Warshall Algorithm as appropriate
Potential Uses of the Floyd-Warshall Algorithm as appropriate
huseindihon
 

Recently uploaded (20)

Histology of Muscle types histology o.ppt
Histology of Muscle types histology o.pptHistology of Muscle types histology o.ppt
Histology of Muscle types histology o.ppt
 
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
 
Towards an Analysis-Ready, Cloud-Optimised service for FAIR fusion data
Towards an Analysis-Ready, Cloud-Optimised service for FAIR fusion dataTowards an Analysis-Ready, Cloud-Optimised service for FAIR fusion data
Towards an Analysis-Ready, Cloud-Optimised service for FAIR fusion data
 
VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Kanpur Girls Call Kanpur 0X0000000X Doorstep High-Profile Girl Service Ca...
 
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
 
the potential of the development of the Ford–Fulkerson algorithm to solve the...
the potential of the development of the Ford–Fulkerson algorithm to solve the...the potential of the development of the Ford–Fulkerson algorithm to solve the...
the potential of the development of the Ford–Fulkerson algorithm to solve the...
 
Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...
Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...
Harnessing Wild and Untamed (Publicly Available) Data for the Cost efficient ...
 
DU degree offer diploma Transcript
DU degree offer diploma TranscriptDU degree offer diploma Transcript
DU degree offer diploma Transcript
 
🚂🚘 Premium Girls Call Guwahati 🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...
🚂🚘 Premium Girls Call Guwahati  🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...🚂🚘 Premium Girls Call Guwahati  🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...
🚂🚘 Premium Girls Call Guwahati 🛵🚡000XX00000 💃 Choose Best And Top Girl Servi...
 
Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...
Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...
Celebrity Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servi...
 
🚂🚘 Premium Girls Call Bangalore 🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...
🚂🚘 Premium Girls Call Bangalore  🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...🚂🚘 Premium Girls Call Bangalore  🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...
🚂🚘 Premium Girls Call Bangalore 🛵🚡000XX00000 💃 Choose Best And Top Girl Serv...
 
Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...
Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...
Exclusive Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service...
 
DataScienceConcept_Kanchana_Weerasinghe.pptx
DataScienceConcept_Kanchana_Weerasinghe.pptxDataScienceConcept_Kanchana_Weerasinghe.pptx
DataScienceConcept_Kanchana_Weerasinghe.pptx
 
History and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big DataHistory and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big Data
 
Why_are_we_hypnotizing_ourselves-_ATeggin-1.pdf
Why_are_we_hypnotizing_ourselves-_ATeggin-1.pdfWhy_are_we_hypnotizing_ourselves-_ATeggin-1.pdf
Why_are_we_hypnotizing_ourselves-_ATeggin-1.pdf
 
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
 
VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...
VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...
VIP Kolkata Girls Call Kolkata 0X0000000X Doorstep High-Profile Girl Service ...
 
Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...
Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...
Female Girls Call Noida 🎈🔥9873940964 🔥💋🎈 Provide Best And Top Girl Service An...
 
Cyber Insurance Mathematical Model & Pricing
Cyber Insurance Mathematical Model & PricingCyber Insurance Mathematical Model & Pricing
Cyber Insurance Mathematical Model & Pricing
 
Potential Uses of the Floyd-Warshall Algorithm as appropriate
Potential Uses of the Floyd-Warshall Algorithm as appropriatePotential Uses of the Floyd-Warshall Algorithm as appropriate
Potential Uses of the Floyd-Warshall Algorithm as appropriate
 

Lab presentation (a framework for understanding unintended consequences of machine learning)

  • 1. A Framework for Understanding Unintended consequences of Machine Learning Author: Harini Suresh (MIT), John V. Guttag(MIT) Presented: Chenguang Xu “Shine”
  • 2. The Problem with Biased data • Various unwanted consequences of ML algorithm arise in some way from biased data. • Bias refers to an unintended or potentially harmful property of the data. • Data is a product of many factors, and is the product of a process
  • 3. An illustrative Scenario Lack of data on women, introducing more data solved the issue. The use of a proxy label (human assessment of quality) versus the true label (actual qualification) allowed the model to discriminate by gender.
  • 4. Five Sources of Bias in ML
  • 5. Historical Bias It is a fundamental, structural issue with the very first step of the data generation process.
  • 6. Representation Bias • It arises when defining and sampling from a population. • It can arise for several reasons: • The sampling methods only reach a portion of the population. • The population of interest has changed or is distinct from the population used during model training.
  • 7. Representation Bias (cont.) Shankar, Shreya, et al. "No classification without representation: Assessing geodiversity issues in open data sets for the developing world." arXiv preprint arXiv:1711.08536 (2017).
  • 8. Representation Bias (cont.) Photos of bridegrooms from different countries aligned by the log-likelihood that the classifier trained on Open Images assigns to the bridegroom class. Shankar, Shreya, et al. "No classification without representation: Assessing geodiversity issues in open data sets for the developing world." arXiv preprint arXiv:1711.08536 (2017).
  • 9. Measurement Bias • It arises when subsequently choosing and measuring the particular features of interest. • It can arise in several ways: • The granularity of data varies across groups. • The quality of data varies across groups. • The defined classification task is an oversimplification.
  • 10. • It arises when a one-size-fit-all model is used for groups with different conditional distributions. Aggregation Bias
  • 11. Evaluation Bias • It occurs when the evaluation and/or benchmark data for an algorithm doesn’t represent the target population. Buolamwini, Joy, and Timnit Gebru. "Gender shades: Intersectional accuracy disparities in commercial gender classification." Conference on Fairness, Accountability and Transparency. 2018.
  • 12. Formalizations and Mitigations • A data generation and ML pipeline viewed as a series of mapping functions. Mitigating Aggregation Bias: • adjusting g • change r or t for transforming the data Mitigating Evaluation Bias: • redefine k • adjusting X, Y ^ ^ Mitigating Representation Bias: • improve s Measurement and historical Bias: • adjust s will likely be ineffective
  • 13.